Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases starting with unusual characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the symbol âĢ, indicating a focus on a specific type of emphasis or representation in speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shroud
    -0.84
    ascus
    -0.75
     recogn
    -0.69
     coerc
    -0.68
    wagen
    -0.68
     dispers
    -0.67
     messenger
    -0.67
     demonstr
    -0.67
    omorphic
    -0.66
     coats
    -0.66
    POSITIVE LOGITS
    ľ
    1.87
    ł
    1.67
    ª
    1.64
    ¡
    1.57
    Ŀ
    1.56
    IJ
    1.54
    ĸ
    1.52
    ¦
    1.50
    ŀ
    1.49
    ij
    1.48
    Act Density 0.072%

    No Known Activations